Slashdot Mirror
Ending Spam
Shalendra Chhabra writes "Jonathan
Zdziarski has been fighting spam since before the first MIT
spam conference in 2003, and has now released a full-on technical
book,
Ending Spam, on spam filtering. Ending Spam
covers how
the current
and near-future crop of heuristic and statistical filters actually work
under the hood, and how you can most effectively use such filters to
protect your inbox." Read on for the rest of Chhabra's review.
Ending Spam: Bayesian Content Filtering and the Art of Statistical Language Classification
author
Jonathan A. Zdziarski
pages
312
publisher
No Starch Press
rating
8
reviewer
Shalendra Chhabra
ISBN
1593270526
summary
Very Good Book Covering Statistical Models and Techniques Implemented in Current Spam Filters
Spam (unsolicited commercial email) and phishing (fraudulent emails) are causing losses of billions of dollars to businesses. Many initiatives are currently underway for fighting this challenge. On the legal front, a Virginia court recently sentenced a prolific spammer, Jeremy Jaynes, to nine years in prison, and a Nigerian court sentenced a woman to two and a half years for phishing. Michigan and Utah have both passed laws creating "do-not-contact" registries in July/August 2005, covering e-mail addresses, instant messaging addresses and telephone numbers. Technical initiatives to fight spam include server- or client-side spam filtering, using Lists (Blacklists, Whitelists, Greylists), Email Authentication Standards (IIM, DK, DKIM, SPF, SenderID), and emerging sender reputation and accreditation services.
Ending Spam is the first book explaining the fine details of the theoretical models and machine-learning algorithms implemented in these filters. The book is divided into three parts: introduction to spam filtering, fundamentals of statistical filtering, and advanced concepts of statistical filtering.
The first section of the book discusses the history of spam, spam kings, different approaches for fighting spam such as blacklisting, whitelisting, heuristic filtering, challenge response, throttling, collaborative filtering, Authenticated SMTP, Sender Policy Framework and SenderID, spammer fingerprinting, etc. However, the author omitted any mention of locally-sensitive hash functions (such as Nilsimsa Hash) to counter spammers' random insertion of words, the use of CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart), Greylisting, Identified Internet Mail, and Domain Keys (now Domain Keys Identified Mail).
In the next chapter, the author clearly explains various components of a Language Classifier Pipeline, including the Historical Dataset (aka wordlist, database, dictionary, filter memory), Tokenizer, and the Analysis Engine with its feedback loop. However, the process flow of a language classifier could have been more generalized, e.g. incorporating an initial text-to-text transformer. This chapter also covers the advantages and disadvantages of various training modes for filters, such as Train Everything (TEFT), Train-on-Error (TOE), and Train Until No Errors (TUNE). This part concludes with the description of Paul Graham's famous spam-filtering technique using Bayesian classification (as described in "A Plan for Spam"), Gary Robinson's Geometric Mean Test, Fisher-Robinsons Inverse Chi Square (including the source code for the inversion function), and some other tricks for optimizing spam- filtering accuracy.
The second part of this book deals with the fundamentals of statistical filtering. The author explains HTML and Base64 encoding, followed by a detailed description of tokenization techniques (e.g. Sparse Binary Polynomial Hashing). Then there's a discussion of the various tricks that spammers use for penetrating filters. Although these tactics are mentioned in John Graham-Cumming's "Spammers Compendium," Jonathan has very elegantly explained why some tricks work for spammers and some don't. This part concludes by addressing some of the resource, storage and scaling concerns raised by the large number of features generated from tokenization techniques.
The third part of this book deals with advanced concepts of statistical filtering. This includes the testing criteria for measuring accuracy of an email filter, and some advanced tokenization concepts, e.g. chained tokens (taking word-pairs and phrases into account, instead of individual words) generated using a sliding 5-byte window as mentioned in Sparse Binary Polynomial Hashing. The next chapter describes the Markovian Model implemented in the CRM114 Discriminator, but the author fails to describe different weighting schemes for features implemented in the Markovian-based version of CRM114. The author then describes the Bayesian Noise Reduction Technique for purging "out of context" data from the mail text. This chapter concludes with a very nice summary of collaborative algorithms and techniques, such as Message Innoculation, Streamlined Blackhole List, Fingerprinting, Automatic Whitelisting, URL Blacklisting, and Honeypot email addresses for snaring spammers' address harvesting bots.
The most interesting part of this book is the appendix, where the author presents interviews with John Graham-Cumming of POPFile, Brian Burton of SpamProbe, Marty Lamb of TarProxy, Bill Yerazunis of CRM114 Discriminator, and Jonathan Zdziarski of DSPAM (himself). I loved this section.
The salient points of the book: it's very easy to read; each chapter begins with a very thought-provoking introduction, and concludes with a crisp "final thoughts" section. The number of technical errors are very few in this print, and the illustrations are of good quality. Since the book is geared more toward the Bayesian and statistical generation of spam filters, the absence of certain spam-busting technologies is acceptable. However, a noticeable omission is the lack of discussion about measuring spam-filter accuracy, and what impact this has on setting filtration thresholds. A section on the economics of tradeoffs, and the use of a Receiver Operating Characteristic curve (ROC) would have been very helpful.
Overall, by putting together Ending Spam, Jonathan Zdziarski has made another significant contribution (after DSPAM) to the anti-spam community. Whether you are a system administrator, anti-spam researcher, engineer or a newbie interested in fighting spam, this book is a great reference.
William S Yerazunis and Richard Jowsey also contributed to this review. Shalendra Chhabra is a Graduate Student in Department of Computer Science and Engineering at University of California, Riverside. He is on the development team of CRM114 Discriminator and has presented his work at MIT Spam Conference 2005, Cisco Systems, and Stanford University. You can purchase Ending Spam: Bayesian Content Filtering and the Art of Statistical Language Classification from bn.com. Slashdot welcomes readers' book reviews -- to see your own review here, read the book review guidelines, then visit the submission page.
Spam (unsolicited commercial email) and phishing (fraudulent emails) are causing losses of billions of dollars to businesses. Many initiatives are currently underway for fighting this challenge. On the legal front, a Virginia court recently sentenced a prolific spammer, Jeremy Jaynes, to nine years in prison, and a Nigerian court sentenced a woman to two and a half years for phishing. Michigan and Utah have both passed laws creating "do-not-contact" registries in July/August 2005, covering e-mail addresses, instant messaging addresses and telephone numbers. Technical initiatives to fight spam include server- or client-side spam filtering, using Lists (Blacklists, Whitelists, Greylists), Email Authentication Standards (IIM, DK, DKIM, SPF, SenderID), and emerging sender reputation and accreditation services.
Ending Spam is the first book explaining the fine details of the theoretical models and machine-learning algorithms implemented in these filters. The book is divided into three parts: introduction to spam filtering, fundamentals of statistical filtering, and advanced concepts of statistical filtering.
The first section of the book discusses the history of spam, spam kings, different approaches for fighting spam such as blacklisting, whitelisting, heuristic filtering, challenge response, throttling, collaborative filtering, Authenticated SMTP, Sender Policy Framework and SenderID, spammer fingerprinting, etc. However, the author omitted any mention of locally-sensitive hash functions (such as Nilsimsa Hash) to counter spammers' random insertion of words, the use of CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart), Greylisting, Identified Internet Mail, and Domain Keys (now Domain Keys Identified Mail).
In the next chapter, the author clearly explains various components of a Language Classifier Pipeline, including the Historical Dataset (aka wordlist, database, dictionary, filter memory), Tokenizer, and the Analysis Engine with its feedback loop. However, the process flow of a language classifier could have been more generalized, e.g. incorporating an initial text-to-text transformer. This chapter also covers the advantages and disadvantages of various training modes for filters, such as Train Everything (TEFT), Train-on-Error (TOE), and Train Until No Errors (TUNE). This part concludes with the description of Paul Graham's famous spam-filtering technique using Bayesian classification (as described in "A Plan for Spam"), Gary Robinson's Geometric Mean Test, Fisher-Robinsons Inverse Chi Square (including the source code for the inversion function), and some other tricks for optimizing spam- filtering accuracy.
The second part of this book deals with the fundamentals of statistical filtering. The author explains HTML and Base64 encoding, followed by a detailed description of tokenization techniques (e.g. Sparse Binary Polynomial Hashing). Then there's a discussion of the various tricks that spammers use for penetrating filters. Although these tactics are mentioned in John Graham-Cumming's "Spammers Compendium," Jonathan has very elegantly explained why some tricks work for spammers and some don't. This part concludes by addressing some of the resource, storage and scaling concerns raised by the large number of features generated from tokenization techniques.
The third part of this book deals with advanced concepts of statistical filtering. This includes the testing criteria for measuring accuracy of an email filter, and some advanced tokenization concepts, e.g. chained tokens (taking word-pairs and phrases into account, instead of individual words) generated using a sliding 5-byte window as mentioned in Sparse Binary Polynomial Hashing. The next chapter describes the Markovian Model implemented in the CRM114 Discriminator, but the author fails to describe different weighting schemes for features implemented in the Markovian-based version of CRM114. The author then describes the Bayesian Noise Reduction Technique for purging "out of context" data from the mail text. This chapter concludes with a very nice summary of collaborative algorithms and techniques, such as Message Innoculation, Streamlined Blackhole List, Fingerprinting, Automatic Whitelisting, URL Blacklisting, and Honeypot email addresses for snaring spammers' address harvesting bots.
The most interesting part of this book is the appendix, where the author presents interviews with John Graham-Cumming of POPFile, Brian Burton of SpamProbe, Marty Lamb of TarProxy, Bill Yerazunis of CRM114 Discriminator, and Jonathan Zdziarski of DSPAM (himself). I loved this section.
The salient points of the book: it's very easy to read; each chapter begins with a very thought-provoking introduction, and concludes with a crisp "final thoughts" section. The number of technical errors are very few in this print, and the illustrations are of good quality. Since the book is geared more toward the Bayesian and statistical generation of spam filters, the absence of certain spam-busting technologies is acceptable. However, a noticeable omission is the lack of discussion about measuring spam-filter accuracy, and what impact this has on setting filtration thresholds. A section on the economics of tradeoffs, and the use of a Receiver Operating Characteristic curve (ROC) would have been very helpful.
Overall, by putting together Ending Spam, Jonathan Zdziarski has made another significant contribution (after DSPAM) to the anti-spam community. Whether you are a system administrator, anti-spam researcher, engineer or a newbie interested in fighting spam, this book is a great reference.
William S Yerazunis and Richard Jowsey also contributed to this review. Shalendra Chhabra is a Graduate Student in Department of Computer Science and Engineering at University of California, Riverside. He is on the development team of CRM114 Discriminator and has presented his work at MIT Spam Conference 2005, Cisco Systems, and Stanford University. You can purchase Ending Spam: Bayesian Content Filtering and the Art of Statistical Language Classification from bn.com. Slashdot welcomes readers' book reviews -- to see your own review here, read the book review guidelines, then visit the submission page.
The openness eill have to pay it's cost. and spam is one such pest. You can develop better strategies for pest control. But in the end it's a trade off.
Java Oracle Linux Enthusiast
Why worry about spam? Bill Gates promised to end spam by early next spring. (It's marked in my calendar along with the link to where he promised, but not with me in my PDA right now.)
While all of these different technological approaches to spam are worth pursuing, they just don't build the same esprit d'corps as a mob with pitchforks and torches at midnight.
If brevity is the soul of wit, then how does one explain Twitter?
is with a knife, a spatula, and a frying pan, preferably over a hot wood fire.
Yum!
-- Tigger warning: This post may contain tiggers! --
As with any book of this type, it is outdated by the time it reaches the shelves. The spam battlefield changes on a daily basis and the tools used to fight the battle, change with it daily.
By the time a book has been written edited, proof read(though many publishers skip this part), type set, printed, distributed and sold, it no longer resembles the technology.
Spam will continue to disguise itself as legit email. You can try to filter it out and set more strict filters but catching legitimate mail is far more likely to happen. In the end, you have to make a trade off and practically accept some spam.
From:
HERE
"ABOUT THE AUTHOR:
Jonathan A. Zdziarski has been fighting spam for eight years, and has spent a significant portion of the past two years working on the next generation spam filter DSPAM. His research in algorithmic theory and neural networking has led to the development of many new approaches in language classification, and he has played a key role in designing some popular algorithms in use today, including Message Inoculation, Bayesian Noise Reduction, and the first functional Neural Networking algorithm for spam filters. Zdziarski lectures widely on the topic of spam and was a speaker at the 2004 and 2005 MIT Spam Conference.
"
You can't talk about Wikipedia's flaws on Wikipedia
If you can't see it, it ain't there?
Heck, our lobby group even points out to Congress how spam laws are not really needed, since people who really don't want the spam are free to filter it. That and a litte payola and we are free to phish for more victims.
Yea, keep "fighting spam" with lame filters, we love it. Thanks!
No Karma is given if one is modded up "funny".
I'm wondering... will UCE (Spam) be like malaria... controllable in most areas but impossible to eradicate?
Or will these dedicated folks and others be able to eliminate it, perhaps by changes to the mail protocols?
Interesting question that, considering my work involves malaria.
My guess is that, like malaria and most parasitic infestations, we will at some point develop a "cure". The "cure" will work for a few years, after which the parasite (spam) will have adapted, surviving until then in different hosts (old windows machines donated to Africa, who knows). Then, having developed a new trick, it will come back as strong as ever.
Biology teaches us that organisms adapt to changing environments, thru selective breeding (natural), point mutations, and unforseen combinations (see the H51N avian influenza). We can develop cures, but once we do so, we can be fairly sure that, baring species extinction, it will develop methods to cope with our cures.
An easy solution would be to move to IPv6 - but this, like authentication, will only kill off the spam which doesn't use "trusted email clients that are identified" while the spam that can survive will be encouraged to spread like wildfire.
So long as the fiscal, legal, and societal penalties for spamming are fairly low and the rewards are high, and while most people do nothing about it, it will spread.
-- Tigger warning: This post may contain tiggers! --
Email, as a system, is fundamentally broken. It's this broken design that allows SPAM to happen in the first place.
Current anti-spam solutions are to email what an Antivirus package is to Windows - a hack add-on that increases complexity and costs without solving the underlying problem(s).
Rather than fight viruses, we should be engineering an O/S that's inherently resistent to them. How many of you Linux/BSD/MacOS users EVER use antivirus, or need to?
Rather than build ever-better antispam filters for Email, we should be engineering an email solution that's inherenly resistant to SPAM.
The answer lies in authentication - who is sending the email. Some of the best technologies now available use degrees of authentication without actually *saying* it outright. Examples are: refusing invalid domains, greylisting, challenge-response, SenderID - all of these are some form of authentication.
As these are, one-by-one bypassed by the spammers, the need for authentication of senders will continue to increase, until the dolts who will invariably reply with that "your solution will not work because... (check the options)" are shown to simply be.... wrong.
Give it time. It's already happening whatever the originators of the SMTP protocol desired.
I have no problem with your religion until you decide it's reason to deprive others of the truth.
The reason spammers do it is that their message reaches people, enough of them to make it worthwhile. So, the more effective and widespread the filters, the less messages that reach people, and the less it's worth. If the filters were really effective, nearly 100%, it would simply not be worth it to spam, you wouldn't make any money because no one would see your message.
I don't think we'll ever get there, but yes filtering really could end spam.
Bad analogy. Spam is not an organism or infection. It is a business model. It does not "survive" in computers, but in a combination of economical, technical and legal conditions. Once those conditions become strongly unfavorable to the business model, there isn't really much that adaption can do. Selling "snake-oil" wonder cures used to be a really big, widespread business model. Better-informed consumers and increased regulation of the market for medicine have all but eradicated this practice. It survives, but in a much-changed and diminished form.
The illegal we do immediately. The unconstitutional takes a little longer.
--Henry Kissinger
If this was published by O'Reilly, I'd have bought it on sight as they bother to edit their books. As it is, I'll give it a wide berth.
This may be the case; however, that doesn't invalidate his work on spam. Remember, Sir Isaac Newton was a firm believer in the more exotic aspects of mystical alchemy, and the vast bulk of his 'research' was complete gibberish. That doesn't make his work on gravity any less valuable.
Reminds me of the conversation at the end of Batman Begins with Gordon and the Bat:
Gordon: "Batman making a stand as he has will only escalate the problem."
If suddenly the masses are educated on spam filtering, wouldn't spammers just adobt tactics to avoid them?
I mean it is afterall a "spammers market". They have increased resources because they're getting all the money. I'm sure the spammers are much smarter than most techies who use filters, they just don't care. They think, "If this techie is going to use a filter to stop my spam so be it, there's a 100 people for each one of him that won't."
No we need to think of new techniques outside of filtering. Filtering is mostly nonsense, manual work. We need something philisophically different than filtering which affects how spam comes through in-transit, or something that affects the financial backing of spammers.
We should be breaking down their lines of communications, etc - not expecting granny to take up spam filtering techniques.
Even a manservant reading all of my mail and hand-carying printouts of nothing but personal messages to my Jamacian bungalow doesn't "end" spam.
It would seem that These Guys are actually making an attempt to "end" spam.
All this guy is just talking about is hiding it from view. Big deal...
Bad analogy. Spam is not an organism or infection. It is a business model. It does not "survive" in computers, but in a combination of economical, technical and legal conditions.
True and False.
Spam acts like a parasitic organism, due to the favorable conditions for the business model. It does, in some cases, actually "survive" in certain computers, which are spam zombies that spew out spam from a spam source - in fact, there are a few at the other UW (in Wisconsin) which utilize the identified computers there to get thru the filters here (in Seattle).
Informing consumers is highly unlikely to stop this behaviour - or else AIDS/HIV would have been halted. Some consumers are highly resistant to changing their behaviour, don't think it's important, or it's such a good deal what would it hurt.
And, like the malarial mosquito, spam uses those responders (infected persons) to download more spam zombie software, since they tend not to be technical enough to remove the infection.
-- Tigger warning: This post may contain tiggers! --
Rule 1 (Spammers always lie) won't change, though occasionally they'll think of new things to lie about. Rule 2 (Spammers are Stupid) won't change, though of course some spammers violate this rule, and some spammers can hire smart people to work for them, and enough of them are sufficiently persistent skr1pt k1dd13z that it sometimes makes up for stupidity.
The latest and greatest spam-blocking technique will last a while before spammers find a way around it - it's somewhat of a losing game, because if it works well enough to be widely popular, it becomes a target for spammers to work around, though if it's effective and obscure, it'll work for you and your friends for a lot longer.
PC users will continue to run insecure operating systems without administering them well, so there'll always be zombies for spammers to abuse. Windows automatic updates will gradually help this, but not only will new OS bugs get discovered frequently, but users will insist on running trojan horses that pretend to be new amusing programs, breaking any semblance of security.
Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
It does, in some cases, actually "survive" in certain computers, which are spam zombies that spew out spam from a spam source
That's not survival in the "organism" analogy, since a zombie will not send spam without a source, which will be gone when the business model is not workable, and especially not cause new source to appear.
like the malarial mosquito, spam uses those responders (infected persons) to download more spam zombie software, since they tend not to be technical enough to remove the infection.
You're mixing up the spreading of "zombie" software that is used to send spam with the spreading of spam itself.
I totally agree that computer worms/viruses work very much like an infectious disease. But they are merely one tool that spammers use, not identical with the phenomenon of spam as such.
The illegal we do immediately. The unconstitutional takes a little longer.
--Henry Kissinger
I totally agree that computer worms/viruses work very much like an infectious disease. But they are merely one tool that spammers use, not identical with the phenomenon of spam as such.
Just as a mosquito is merely a tool the malarial parasite uses to spread itself.
Let's say we knock out something that permits mosquitos to infect human hosts. Chances are that it might only partially impact malarial infections of non-human hosts. The impacted malarial bug, provided it survives and breeds, may then decide to use another vector to complete the infection.
Same with spam - we can knock out the zombies. We can knock out the spam kingpins. We can make the email transmission more secure - it migrates to cell phones or text messages or video messages. Unless we go for species extinction, it is likely that it won't die, but will instead change.
Nowadays I rarely see pop-under ads any more - due to using different browsers - but now ads show up that are movies, which really burn up my bandwidth. To kill off those ads, I would have to disable the very useful site portions that i do want.
So long as the evolutionary niche exists that permits spamsters to make a buck or two from sending spam, so long as people don't turn in most spam, so long as some people buy from spamsters, and so long as most spamsters don't serve long jail sentences and are never caught, it is highly unlikely that spam will cease to exist.
-- Tigger warning: This post may contain tiggers! --
Spam may not be an organism or an infection, but the people who send it are. So I think it is a perfect analogy.
If they're adopting SenderID, it makes it easy to filter them. You can't filter just on the existence of SenderID; you need to check who the sender is and ignore email from known spammers.
That's a good thing. It lets them spew all of the email they want; let's call it freedom of speech (since I don't want any legal limitations on spam also being used to prevent legitimate speech). And I get to ignore them; I can filter them at the SMTP layer even before they get to send the whole message.
It may not be successful yet, if people are misusing the technology by trusting the existence of a Sender ID record to mean it's not spam. But don't blame the technology for being misused.
No, because the anti-spam measures do not aim to kill those people, only to make them stop sending spam. Furthermore, spammers are not a separate species and do not reproduce (as spammers).
The illegal we do immediately. The unconstitutional takes a little longer.
--Henry Kissinger
Just as a mosquito is merely a tool the malarial parasite uses to spread itself.
Except that spam does not use zombies to spread itself, SPAMMERS use zombies to spread spam.
Your analogy is simply flawed. Spam is NOT an organism. It does NOT "survive" somewhere, adapt and spread from the places where it survived.
And we certainly DO go for "species extinction", by eliminating the conditions that make spam practicable and profitable. You enumerate some of those conditions yourself in the end.
The illegal we do immediately. The unconstitutional takes a little longer.
--Henry Kissinger
No, because the anti-spam measures do not aim to kill those people
Yet.
Except that spam does not use zombies to spread itself, SPAMMERS use zombies to spread spam.
Your analogy is simply flawed. Spam is NOT an organism. It does NOT "survive" somewhere, adapt and spread from the places where it survived.
And we certainly DO go for "species extinction", by eliminating the conditions that make spam practicable and profitable. You enumerate some of those conditions yourself in the end.
If it looks like a duck, and it quacks like a duck, and it paddles like a duck, you want me to check to see if it's a robotic assembly of nanobots pretending to be a duck.
Nah. My point is/was - not that I brought up the biological equivalency of spam to malaria (someone else did, and i said it isn't, but it could be thought of that way) - that even should we find a "cure" for spam, it would come back so long as the underlying model rewarded the spamsters in some way to continue to perpetuate.
So long as up to half the population won't report spam - in fact, it's more like 99 percent;
So long as enough people buy from spamsters to make it economically rewarding - which it is;
So long as the penalty is remote enough or far enough in the future to be ignored - which it is;
And so long as society encourages the pursuit of wealth above moral/ethical standards - which it does;
This won't change.
Sure, you can plug up a hole in the dike. I can - and do - turn in spamsters. But they will migrate and adapt.
Are they infectious diseases? Sometimes, see the use of zombies.
Can we truly eradicate them - no, because people will replace the prior spamsters so long as the afore-mentioned conditions perpetuate.
Want to cut down malaria? First, find easy methods of improving sanitation that allows it to perpetuate. Then find ways to interfere with the malarial infection of humans. If you do it backwards, it's likely that many places will still spread it. Because not everyone is rich like we are.
Same goes for spam - find ways to make it unrewarding for people to buy from spamsters (e.g. sell Viagra etc cheap, offer open source versions of office cheap - that's what they sell), find ways to make it bad to be a spamster, and then batten down the hatches with new protocols.
-- Tigger warning: This post may contain tiggers! --
Blacklist everyone, then whitelist only those people who you really want to communicate with. I've been doing it for years and get ZERO spam. People argue that they will miss important messages - nope, I never have. Email is not the only form of communication. All my family, friends, business clients know how to use the phone if their emails bounce. I have a web form (and phone number) for new clients (and once verified they are whitelisted), and I don't give a shit about the few messages that might not make it (although after several years of using this method I have no evidence that I've missed even one).
Greylisting solves 95% for me - seriously. Try Postgrey for an easy, built-in solution to use with Postfix - it works like crazy.
bad_outlook
--
Is this vague enough for you?